Role- AI ArchitectLocation- Brussels, BelgiumExperience level- 15+ YearsJob Description:Architecture & Solution DesignDefine reference architectures for GenAI systems: RAG, agentic orchestration, tool/function calling, multi-step reasoning workflows, memory patterns, and context strategies.Design multi-tenant and enterprise-scale GenAI platforms with clear separation of concerns: UI, orchestration, retrieval, inference, evaluation, and observability.Select model strategies: hosted LLMs, open-weight models, fine-tuning vs. prompt/RAG, latency and cost tradeoffs, and deployment patterns.2) Agentic AI Orchestration & ToolingArchitect agent systems (single/multi-agent) including:Task decomposition, planners/executors, reflection/verification loopsTool use patterns (APIs, databases, search, workflow engines)Guardrails to prevent unsafe tool actions and hallucinated commandsBuild reliable flows for “human-in-the-loop” decision points and approvals (e.G., procurement, customer comms, incident triage).3) Retrieval, Knowledge Systems & Data DesignLead design of knowledge ingestion pipelines:document parsing, chunking strategies, embeddings, metadata, lineage, freshness SLAsArchitect vector search and hybrid retrieval:semantic + keyword, reranking, filtering, ACL-aware retrievalEnsure retrieval respects access control, PII handling, data residency, and auditability.4) Production Engineering, Reliability & CostSet non-functional requirements for GenAI workloads:SLOs, latency budgets, fallback models, caching, rate limitingDesign cost controls: prompt/token optimization, model routing, batching, and usage governance.Implement resiliency patterns: circuit breakers, retries, queue-based orchestration, idempotency.5) Security, Risk & Responsible AIEstablish AI security posture:prompt injection defenses, data exfiltration controls, tool sandboxingDefine policies and controls for:sensitive data, logging, redaction, encryption, secret management, and auditingCollaborate with risk/compliance to drive:model governance, content safety, bias/quality monitoring, and regulatory alignment6) Evaluation, Observability & Continuous ImprovementCreate evaluation frameworks:offline evals (golden sets), automated regression, and scenario-based testingInstrument systems for observability:traces, prompt/versioning, retrieval diagnostics, tool-call logs, and outcome metricsRun A/B tests and iterate on prompts, retrieval, and agent policies based on measurable outcomes.7) Leadership & Stakeholder ManagementPartner with product leaders to identify high-value use cases and define roadmap.Mentor engineers and data scientists on best practices for LLM apps.Produce architecture artifacts: ADRs, threat models, system diagrams, runbooks.Required Skills & ExperienceCore Technical Skills (Must Have)8+ years in software/solution architecture with 2+ years delivering GenAI/LLM solutions in production (adjust as needed).Strong knowledge of LLMs: prompting patterns, context windows, tool/function calling, model limitations, and safety risks.Agentic AI design experience:orchestrators, workflows, multi-step reasoning, tool usage, HITL patternsRAG expertise:embeddings, vector DBs, hybrid retrieval, reranking, chunking strategies, evaluationCloud architecture (Azure/AWS/GCP) with production engineering rigor:microservices, containers (Docker/K8s), serverless, CI/CDSolid programming skills (one or more):Python, TypeScript/JavaScript, Java, C#Experience with APIs and integration patterns:REST/gRPC, event-driven systems, queues, workflow enginesSecurity & Governance (Must Have)Understanding of GenAI-specific threats:prompt injection, data leakage, jailbreaks, insecure tool callingFamiliarity with enterprise controls:IAM, key management, encryption, network isolation, audit loggingResponsible AI practices:evaluation, content moderation, privacy, and compliance-by-designArchitecture & Systems Skills (Must Have)Distributed system design:scalability, fault tolerance, caching, performance tuningObservability:logging/metrics/tracing, prompt/version tracking, monitoring SLIs/SLOsCost management and performance optimization:model selection/routing, token reduction, caching, batchingPreferred / Nice-to-Have SkillsFine-tuning approaches:LoRA/QLoRA, instruction tuning, adapters, distillation (when appropriate)Experience with:Knowledge graphs, semantic layers, enterprise searchAdvanced evaluation:LLM-as-judge with safeguards, rubric scoring, adversarial testingMLOps/LLMOps toolchains:experiment tracking, feature stores, model registries, data quality toolsDomain experience:customer support automation, developer productivity copilots, IT ops agents, finance or healthcare complianceExperience building platforms:reusable agent frameworks, reusable RAG components, multi-team enablementFor more information on how we process your personal data, please refer to HCLTech’s Candidate Data Privacy Notice.